| Use Keras experiment to transfer style |  |
|---|---|
 |
This notebook contains the steps and code required to demonstrate style transfer techique using Watson Machine Learning Service. This notebook introduces commands for getting data, training_definition persistance to Watson Machine Learning repository and model training.
Some familiarity with Python is helpful. This notebook uses Python 3.6 and Watson Studio environments.
Learning goals¶
In this notebook you learn to work with Watson Machine Learning experiments to train Deep Learning models (Keras).
Contents¶
1. Set up¶
Before you use the sample code in this notebook, you must perform the following setup tasks:
- Create a Watson Machine Learning (WML) Service instance (a free plan is offered and information about how to create the instance is here).
- Create a Cloud Object Storage (COS) instance (a lite plan is offered and information about how to order storage is here).
Note: When using Watson Studio, you already have a COS instance associated with the project you are running the notebook in. Create new credentials with HMAC:
- Go to your COS dashboard.
- In the Service credentials tab, click New Credential+.
Add the inline configuration parameter: {"HMAC":true}, click Add. (For more information, see HMAC.)
This configuration parameter adds the following section to the instance credentials, (for use later in this notebook):
"cos_hmac_keys": { "access_key_id": "-------", "secret_access_key": "-------" }
In this section:
1.1 Work with Cloud Object Storage (COS)¶
Import the Boto library, which allows Python developers to manage COS.
!pip install --upgrade keras==2.2.4
# Import the boto library
import ibm_boto3
from ibm_botocore.client import Config
import os
import json
import warnings
import urllib
import time
Authenticate to COS and define the endpoint you will use.
Enter your COS credentials in the following cell. You can find these credentials in your COS instance dashboard under the Service credentials tab as described in the set up section.
Go to the Endpoint tab in the COS instance's dashboard to get the endpoint information, for example:
s3-api.us-geo.objectstorage.softlayer.net.
# Enter your COS credentials.
cos_credentials = {
"apikey": "***",
"cos_hmac_keys": {
"access_key_id": "***",
"secret_access_key": "***"
},
"endpoints": "https://cos-service.bluemix.net/endpoints",
"iam_apikey_description": "***",
"iam_apikey_name": "***",
"iam_role_crn": "crn:v1:bluemix:public:iam::::serviceRole:Writer",
"iam_serviceid_crn": "***",
"resource_instance_id": "***"
}
api_key = cos_credentials['apikey']
service_instance_id = cos_credentials['resource_instance_id']
auth_endpoint = 'https://iam.bluemix.net/oidc/token'
# Enter your Endpoint information.
service_endpoint = 'https://s3-api.us-geo.objectstorage.softlayer.net'
Create the Boto resource by providing type, endpoint_url and credentials.
cos = ibm_boto3.resource('s3',
ibm_api_key_id=api_key,
ibm_service_instance_id=service_instance_id,
ibm_auth_endpoint=auth_endpoint,
config=Config(signature_version='oauth'),
endpoint_url=service_endpoint)
Create the buckets you will use to store training data and training results.
Note: Bucket names must be unique.
# Create two buckets, style-data-example and style-results-example
from uuid import uuid4
bucket_uid = str(uuid4())
buckets = ['style-data-example-' + bucket_uid, 'style-results-example-' + bucket_uid]
for bucket in buckets:
if not cos.Bucket(bucket) in cos.buckets.all():
print('Creating bucket "{}"...'.format(bucket))
try:
cos.create_bucket(Bucket=bucket)
except ibm_boto3.exceptions.ibm_botocore.client.ClientError as e:
print('Error: {}.'.format(e.response['Error']['Message']))
You have now created two new buckets:
style-data-examplestyle-results-example
Display a list of buckets for your COS instance to verify that the buckets were created.
# Display the buckets
print(list(cos.buckets.all()))
1.2 Download training data and upload it to COS buckets¶
Download your training data and upload them to the 'training-data' bucket. Then, create a list of links for the training dataset.
The following code snippet creates the STYLE_DATA folder and downloads the files from the links to the folder.
Tip: First, use the !pip install wget command to install the wget library:
!pip install --upgrade wget
import wget, os
# Create folder
data_dir = 'STYLE_DATA'
if not os.path.isdir(data_dir):
os.mkdir(data_dir)
links = ['https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
'https://upload.wikimedia.org/wikipedia/commons/thumb/e/ea/Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg/1513px-Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg',
'https://upload.wikimedia.org/wikipedia/commons/5/52/Krak%C3%B3w_239a.jpg',
'https://upload.wikimedia.org/wikipedia/commons/3/3f/Kandinsky%2C_Lyrisches.jpg']
# Download the links to the folder
for i in range(len(links)):
if 'Gogh' in links[i]:
filepath = os.path.join(data_dir, 'van_gogh.jpg')
elif 'Krak' in links[i]:
filepath = os.path.join(data_dir, 'krakow.jpg')
elif 'Kandinsky' in links[i]:
filepath = os.path.join(data_dir, 'kandinsky.jpg')
else:
filepath = os.path.join(data_dir, os.path.join(links[i].split('/')[-1]))
if not os.path.isfile(filepath):
print(links[i])
urllib.request.urlretrieve(links[i], filepath)
# List the files in the STYLE_DATA folder
!ls STYLE_DATA
Base image: Cracow - main market square¶
from IPython.display import Image
Image(filename=os.path.join(data_dir, 'krakow.jpg'), width=1000)
Style image 1: Vincent Van Gogh - Starry Night¶
Image(filename=os.path.join(data_dir, 'van_gogh.jpg'), width=500)
Style image 2: Kandinsky Lyrisches¶
Image(filename=os.path.join(data_dir, 'kandinsky.jpg'), width=600)
Upload the data files to the created buckets.
bucket_name = buckets[0]
bucket_obj = cos.Bucket(bucket_name)
for filename in os.listdir(data_dir):
with open(os.path.join(data_dir, filename), 'rb') as data:
bucket_obj.upload_file(os.path.join(data_dir, filename), filename)
print('{} is uploaded.'.format(filename))
Let's see the list of all the buckets and their contents.
for obj in bucket_obj.objects.all():
print('Object key: {}'.format(obj.key))
print('Object size (kb): {}'.format(obj.size/1024))
You are done with COS, and you are now ready to train your model!
1.3 Work with the Watson Machine Learning instance¶
Load the libraries you need.
import urllib3, requests, json, base64, time, os
Authenticate to the Watson Machine Learning (WML) service on IBM Cloud.
Tip: Authentication information (your credentials) can be found in the Service credentials tab of the service instance that you created on IBM Cloud. If there are no credentials listed for your instance in Service credentials, click New credential (+) and enter the information required to generate new authentication information.
Action: Enter your WML service instance credentials here.
wml_credentials = {
"apikey": "***",
"instance_id": "***",
"password": "***",
"url": "https://ibm-watson-ml.mybluemix.net",
"username": "***"
}
Install the watson-machine-learning-client from pypi.¶
!pip install --upgrade watson-machine-learning-client
Import the watson-machine-learning-client and authenticate to the service instance.¶
from watson_machine_learning_client import WatsonMachineLearningAPIClient
client = WatsonMachineLearningAPIClient(wml_credentials)
print(client.version)
Note: watson-machine-learning-client documentation can be found here.
2. Create the training definitions¶
2.1 Prepare the training definition metadata¶
Hint: The final effect depends on number of iterations, and that the number of iterations impacts the training time.
#Set the number of iterations.
iters = 1
model_definition_1_metadata = {
client.repository.DefinitionMetaNames.NAME: "style transfer van gogh",
client.repository.DefinitionMetaNames.FRAMEWORK_NAME: "tensorflow",
client.repository.DefinitionMetaNames.FRAMEWORK_VERSION: "1.14",
client.repository.DefinitionMetaNames.RUNTIME_NAME: "python",
client.repository.DefinitionMetaNames.RUNTIME_VERSION: "3.6",
client.repository.DefinitionMetaNames.EXECUTION_COMMAND: "python style_transfer.py krakow.jpg van_gogh.jpg krakow --iter " + str(iters)
}
model_definition_2_metadata = {
client.repository.DefinitionMetaNames.NAME: "style transfer kandinsky",
client.repository.DefinitionMetaNames.FRAMEWORK_NAME: "tensorflow",
client.repository.DefinitionMetaNames.FRAMEWORK_VERSION: "1.14",
client.repository.DefinitionMetaNames.RUNTIME_NAME: "python",
client.repository.DefinitionMetaNames.RUNTIME_VERSION: "3.6",
client.repository.DefinitionMetaNames.EXECUTION_COMMAND: "python style_transfer.py krakow.jpg kandinsky.jpg krakow --iter " + str(iters)
}
2.2 Get the sample model definition content files from Git¶
!rm -rf STYLE.zip
filename_definition = 'STYLE.zip'
if not os.path.isfile(filename_definition):
!wget https://github.com/pmservice/wml-sample-models/raw/master/keras/style/definition/STYLE.zip
!ls STYLE.zip
2.3 Store the training definition in the WML repository¶
Store definition 1¶
definition_details = client.repository.store_definition(filename_definition, model_definition_1_metadata)
definition_url = client.repository.get_definition_url(definition_details)
definition_uid = client.repository.get_definition_uid(definition_details)
print(definition_url)
Store definition 2¶
definition_2_details = client.repository.store_definition(filename_definition, model_definition_2_metadata)
definition_2_url = client.repository.get_definition_url(definition_2_details)
definition_2_uid = client.repository.get_definition_uid(definition_2_details)
print(definition_2_url)
List the stored definitions¶
client.repository.list_definitions()
3. Create the experiment definition¶
Get a list of supported configuration parameters.
client.repository.ExperimentMetaNames.show()
Create an experiment, which will train two models based on previously stored definitions.
TRAINING_DATA_REFERENCE = {
"connection": {
"endpoint_url": service_endpoint,
"access_key_id": cos_credentials['cos_hmac_keys']['access_key_id'],
"secret_access_key": cos_credentials['cos_hmac_keys']['secret_access_key']
},
"source": {
"bucket": buckets[0],
},
"type": "s3"
}
TRAINING_RESULTS_REFERENCE = {
"connection": {
"endpoint_url": service_endpoint,
"access_key_id": cos_credentials['cos_hmac_keys']['access_key_id'],
"secret_access_key": cos_credentials['cos_hmac_keys']['secret_access_key']
},
"target": {
"bucket": buckets[1],
},
"type": "s3"
}
experiment_metadata = {
client.repository.ExperimentMetaNames.NAME: "STYLE experiment",
client.repository.ExperimentMetaNames.TRAINING_DATA_REFERENCE: TRAINING_DATA_REFERENCE,
client.repository.ExperimentMetaNames.TRAINING_RESULTS_REFERENCE: TRAINING_RESULTS_REFERENCE,
client.repository.ExperimentMetaNames.TRAINING_REFERENCES: [
{
"name": "van gogh - cracow",
"training_definition_url": definition_url,
"compute_configuration": {"name": "k80x4"}
},
{
"name": "kandinsky - cracow",
"training_definition_url": definition_2_url,
"compute_configuration": {"name": "k80x4"}
},
],
}
Store the experiment in the WML repository.
# Store the experiment and display the experiment_uid.
experiment_details = client.repository.store_experiment(meta_props=experiment_metadata)
experiment_uid = client.repository.get_experiment_uid(experiment_details)
print(experiment_uid)
List the stored experiments.
client.repository.list_experiments()
Get the experiment definition details
details = client.repository.get_experiment_details(experiment_uid)
4. Run the experiment¶
Tip: To run the experiment in the background, set the optional parameter asynchronous=True (or remove it).
experiment_run_details = client.experiments.run(experiment_uid, asynchronous=False)
As you can see, the experiment run has finished.
Get the experiment run UID.¶
experiment_run_id = client.experiments.get_run_uid(experiment_run_details)
print(experiment_run_id)
Get the run details.¶
The code in the following cell gets details about a particular experiment run.
run_details = client.experiments.get_run_details(experiment_run_id)
run_details
Get the experiment run status.¶
Call client.experiments.get_status(run_uid) to check the experiment run status. This is useful when you run an experiment in the background.
status = client.experiments.get_status(experiment_run_id)
print(status)
Monitor the experiment run.¶
Call client.experiments.monitor_logs(run_uid) to monitor the experiment run. This method streams the training logs content to the console.
client.experiments.monitor_logs(experiment_run_id)
List the training runs triggered by experiment run.¶
client.experiments.list_training_runs(experiment_run_id)
As you can see, two training runs completed.
# List the training uids.
# training_uids = client.experiments.get_training_uids(experiment_run_details)
training_uids = [run_details['entity']['training_statuses'][i]['results']['reference']['location']['model_location'] for i in [0,1]]
print(training_uids)
5. Results - transferred styles images¶
bucket_name = buckets[1]
bucket_obj = cos.Bucket(bucket_name)
transfered_images = []
for uid in training_uids:
obj = bucket_obj.Object(uid + '/transfered_images/krakow_at_iteration_' + str(iters-1) + '.png')
filename = 'krakow_transfered_' + str(uid) + '.jpg'
transfered_images.append(filename)
with open(filename, 'wb') as data:
obj.download_fileobj(data)
print(filename)
Cracow¶
Have a look at the original picture again.
Image(filename=os.path.join(data_dir, 'krakow.jpg'), width=1000)
Cracow + Van Gogh, Cracow + Kandinsky¶
Display the pictures after Van Gogh and Kandinsky styles have been applied.
Image(filename=transfered_images[1], width=1000)
Image(filename=transfered_images[0], width=1000)
6. Summary¶
You successfully completed this notebook! You learned how to use watson-machine-learning-client to run experiments. Check out our:
- Sample python web application for style transfer
- Online Documentation for more samples, tutorials, documentation, how-tos, and blog posts
Citations¶
- Rj1979, Kraków 239a, marked as public domain, more details on Wikimedia Commons
- Vincent van Gogh, Van Gogh - Starry Night - Google Art Project, marked as public domain, more details on Wikimedia Commons
- Wassily Kandinski, Kandinsky, Lyrisches, marked as public domain, more details on Wikimedia Commons
Author¶
Lukasz Cmielowski, PhD, is an Automation Architect and Data Scientist at IBM with a track record of developing enterprise-level applications that substantially increases clients' ability to turn data into actionable knowledge.
Copyright © 2018, 2019 IBM. This notebook and its source code are released under the terms of the MIT License.
Share it with your colleagues and help them discover the power of Watson Studio! Sign Up